VIEW-INVARIANT ACTION RECOGNITION BASED ON ARTIFICIAL NEURAL NETWORKS (2012)

                        View-invariant action recognition based on Artificial                                                                         Neural Networks (2012)

ABSTRACT:

                                    In this paper, a novel view invariant action recognition method based on neural network representation and recognition is proposed. The novel representation of action videos is based on learning spatially related human body posture prototypes using Self Organizing Maps (SOM). Fuzzy distances from human body posture prototypes are used to produce a time invariant action representation. Multilayer perceptron’s are used for action classification. The algorithm is trained using data from a multi-camera setup.

                         An arbitrary number of cameras can be used in order to recognize actions using a Bayesian framework. The proposed method can also be applied to videos depicting interactions between humans, without any modification. The use of information captured from different viewing angles leads to high classification performance. The proposed method is the first one that has been tested in challenging experimental setups, a fact that denotes its effectiveness to deal with most of the open issues in action recognition.

EXISTING SYSTEM:

                        The recognition of human activities has a wide range of promising applications such as smart surveillance, perceptual interfaces, interpretation of sport events, etc. Although there has been much work on human motion analysis over the past two decades, activity understanding still remains challenging.

                        In terms of higher-level analysis, previous studies generally fall under two major categories of approaches. The former usually characterizes the spatiotemporal distribution generated by the motion in its continuum.

DISADVANTAGES OF EXISTING SYSTEM:

            Action recognition methods suffer from many drawbacks in practice, which include

                        (1) The inability to cope with incremental recognition problems;

                        (2) The requirement of an intensive training stage to obtain good performance;

                        (3) The inability to recognize simultaneous multiple actions; and

                        (4) Difficulty in performing recognition frame by frame

PROPOSED SYSTEM:

                       

                        In this paper, a novel view invariant action recognition method based on neural network representation and recognition is proposed.

                        The main contributions of this paper are: a) the use of Self Organizing Maps (SOM) for identifying the basic posture prototypes of all the actions, b) the use of cumulative fuzzy distances from the SOM in order to achieve time-invariant action representations, c) the use of a Bayesian framework to combine the recognition results produced for each camera, d) the solution of the camera viewing angle identification problem using combined neural networks.

ADVANTAGES OF PROPOSED SYSTEM:

                       

                        To establish an effective action recognition method using analysis of spatiotemporal silhouettes measured during the activities, based on the idea that spatiotemporal variations of human silhouettes encode not only spatial information about body poses at certain instants, but also dynamic information  about global body motion and the motions of local body parts. It appears to be feasible to use features that can be obtained from space-time shapes for exploring the action properties. In contrast to feature tracking, extracting space-time shapes is also easier to implement using current vision technologies, especially in the case of stationary cameras.

                        The proposed method has several desirable properties: a) It is easier to comprehend and implement, without the requirements of explicit feature tracking and complex probabilistic modeling of motion patterns; b) being based on binary silhouette analysis, it naturally avoids some problems arising in most previous methods, e.g., unreliable 2-D or 3D tracking, expensive and sensitive optical flow computation, and c) it obtains good results on a large and  challenging database and exhibits considerable robustness. 

MODULES:

o   Pre-processing Module

o   Segmentation

o   Action Recognition Module

o   Action Detection Module

o   Output Module

MODULE DESCRIPTION:

Pre Processing Module:

                        This is the first module. This module is to convert the input video to images. And we have to do the image enhancement (i.e.: Noise removal etc…). Image get from the video is extracted into frames.

Segmentation

                        Edges can be detected from the frames. For detection we have to convert the image to black and white using gray scale .For edge detection we have to use canny edge detection algorithm.

Action Recognition

                        We have to store the edges into the Files. This module is to find the human action with the use of stored files.

Action Detection

                        Comparison with the files in this section with the input image. This module will do the main processing in this project.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

•                     SYSTEM             : Pentium IV 2.4 GHz

•                     HARD DISK        : 40 GB

•                     FLOPPY DRIVE  : 1.44 MB

•                     MONITOR           : 15 VGA color

•                     MOUSE               : Logitech.

•                     RAM                    : 256 MB

•                     KEYBOARD       : 110 keys enhanced.

SOFTWARE REQUIREMENTS:

            •                     Operating system           :-  Windows XP Professional

            •                     Front End             :-  Microsoft Visual Studio .Net 2008

            •                     Coding Language :-  C# .NET